Exploring a Unified ASR for Multiple South Indian Languages Leveraging Multilingual Acoustic and Language Models

Anoop, CS and Ramakrishnan, AG (2023) Exploring a Unified ASR for Multiple South Indian Languages Leveraging Multilingual Acoustic and Language Models. In: 2022 IEEE Spoken Language Technology Workshop, SLT 2022, 9 - 12 January 2023, Doha, pp. 830-837.

PDF slt_2022.pdf - Published Version Restricted to Registered users only Download (432kB) | Request a copy

Abstract

We build a single automatic speech recognition (ASR) model for several south Indian languages using a common set of intermediary labels, which can be easily mapped to the desired native script through simple lookup tables and a few rules. We use Sanskrit Library Phonetic encoding as the labeling scheme, which exploits the similarity in pronunciation across character sets of multiple Indian languages. Unlike the general approaches, which leverage common label sets only for multilingual acoustic modeling, we also explore multilingual language modeling. Our unified model improves the ASR performance in languages with limited amounts of speech data and also in out-of-domain test conditions. Also, the model performs reasonably well in languages with good representation in the training data. © 2023 IEEE.

Item Type:	Conference Paper
Publication:	2022 IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	The copyright for this article belongs to Institute of Electrical and Electronics Engineers Inc.
Keywords:	Acoustic Modeling; Computational linguistics; Speech recognition; Table lookup, Automatic speech recognition; Conformer; Kannada; Language model; Low resourced language; Multilingual acoustic models; Multilingual language model; Sanskrit; Telugu; Transformer, Modeling languages
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	25 Feb 2023 08:22
Last Modified:	25 Feb 2023 08:22
URI:	https://eprints.iisc.ac.in/id/eprint/80690

Actions (login required)

View Item